提出新方法缓解测试时自适应中的过自信问题，提升模型稳定性与准确性。
COME: Test-time adaption by Conservatively Minimizing Entropy
- 用狄利克雷先验建模预测不确定性，实现保守置信度
- 在多种场景下准确率最高提升34.5%，误报率降低15.1%
- 适合需要可靠推理的开放世界部署场景
机器学习模型需在开放世界中持续适应新数据分布。熵最小化（EM）虽是现有测试时自适应（TTA）方法的核心原则，但其致命缺陷——过自信——常导致模型崩溃。为此，本文提出保守熵最小化（COME），作为传统EM的即插即用替代方案，有效解决该问题。本质上，COME在TTA过程中对模型预测显式建模狄利克雷先验分布以刻画不确定性，从而自然地引导模型在不可靠样本上保持保守置信度。理论上，我们初步分析表明，通过引入数据自适应熵下界，COME能增强优化稳定性。实验上，本方法在常用基准上达到领先性能，在标准、长期和开放世界TTA设置下均有显著提升：准确率最高提升34.5%，误报率降低15.1%。
原文摘要 · Abstract (English)
Machine learning models must continuously self-adjust themselves for novel data distribution in the open world. As the predominant principle, entropy minimization (EM) has been proven to be a simple yet effective cornerstone in existing test-time adaption (TTA) methods. While unfortunately its fatal limitation (i.e., overconfidence) tends to result in model collapse. For this issue, we propose to Conservatively Minimize the Entropy (COME), which is a simple drop-in replacement of traditional EM to elegantly address the limitation. In essence, COME explicitly models the uncertainty by characterizing a Dirichlet prior distribution over model predictions during TTA. By doing so, COME naturally regularizes the model to favor conservative confidence on unreliable samples. Theoretically, we provide a preliminary analysis to reveal the ability of COME in enhancing the optimization stability by introducing a data-adaptive lower bound on the entropy. Empirically, our method achieves state-of-the-art performance on commonly used benchmarks, showing significant improvements in terms of classification accuracy and uncertainty estimation under various settings including standard, life-long and open-world TTA, i.e., up to $34.5\%$ improvement on accuracy and $15.1\%$ on false positive rate.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。